Machine learning search for variable stars

Abstract

Photometric variability detection is often considered as a hypothesis testing problem: an object is variable if the null-hypothesis that its brightness is constant can be ruled out given the measurements and their uncertainties. Uncorrected systematic errors limit the practical applicability of this approach to high-amplitude variability and well-behaving data sets. Searching for a new variability detection technique that would be applicable to a wide range of variability types while being robust to outliers and underestimated measurement uncertainties, we propose to consider variability detection as a classification problem that can be approached with machine learning. We compare several classification algorithms: Logistic Regression (LR), Support Vector Machines (SVM), k-Nearest Neighbors (kNN) Neural Nets (NN), Random Forests (RF) and Stochastic Gradient Boosting classifier (SGB) applied to 18 features (variability indices) quantifying scatter and/or correlation between points in a light curve. We use a subset of OGLE-II Large Magellanic Cloud (LMC) photometry (30265 light curves) that was searched for variability using traditional methods (168 known variable objects identified) as the training set and then apply the NN to a new test set of 31798 OGLE-II LMC light curves. Among 205 candidates selected in the test set, 178 are real variables, 13 low-amplitude variables are new discoveries. We find that the considered machine learning classifiers are more efficient (they find more variables and less false candidates) compared to traditional techniques that consider individual variability indices or their linear combination. The NN, SGB, SVM and RF show a higher efficiency compared to LR and kNN.

19 pages, 13 figures, 5 tables; accepted to MNRAS

References in corpus (17)

• The All-Sky Automated Survey for Supernovae (ASAS-SN) Light Curve Server v1.0
• Limits on the Macho Content of the Galactic Halo from the EROS-2 Survey of the Magellanic Clouds
• The first WASP public data release
• Comparative performance of selected variability detection techniques in photometric time series
• The EPOCH Project: I. Periodic variable stars in the EROS-2 LMC database
• The BRITE Constellation nanosatellite mission: Testing, commissioning and operations
• BRITE-Constellation: Data processing and photometry
• A machine learned classifier for RR Lyrae in the VVV survey
• Data augmentation for machine learning redshifts applied to SDSS galaxies
• Astrokit -- an Efficient Program for High-Precision Differential CCD Photometry and Search for Variable Stars
• First results of the Kourovka Planet Search: discovery of transiting exoplanet candidates in the first three target fields
• Improved Variable Star Search in Large Photometric Data Sets -- New Variables in CoRoT Field LRa02 Detected by BEST II
• Searching transients in large-scale surveys. A method based on the Abbe value
• Gaia Data Release 1: The variability processing & analysis and its application to the south ecliptic pole region
• Color and Variability Characteristics of Point Sources in the Faint Sky Variability Survey
• Machine learning techniques to select Be star candidates. An application in the OGLE-IV Gaia south ecliptic pole field
• A sample of GHz-peaked spectrum sources selected at RATAN-600: spectral and variability properties

Cited by in corpus (3)

• Machine Learning for the Zwicky Transient Facility
• Identification of Young Stellar Object candidates in the $Gaia$ DR2 x AllWISE catalogue with machine learning methods
• Star formation rates and stellar masses from machine learning